Related papers: GroPrompt: Efficient Grounded Prompting and Adapta…
Remote sensing video referring object segmentation (RS-RVOS) is challenged by weak target saliency and severe visual information truncation in dynamic scenes, making it extremely difficult to maintain discriminative target representations…
Most state-of-the-art semi-supervised video object segmentation methods rely on a pixel-accurate mask of a target object provided for the first frame of a video. However, obtaining a detailed segmentation mask is expensive and…
Recent advances in visual grounding have largely shifted away from traditional proposal-based two-stage frameworks due to their inefficiency and high computational complexity, favoring end-to-end direct reference paradigms. However, these…
Traditional reference segmentation tasks have predominantly focused on silent visual scenes, neglecting the integral role of multimodal perception and interaction in human experiences. In this work, we introduce a novel task called…
Open-vocabulary object detection in remote sensing commonly relies on text-only prompting to specify target categories, implicitly assuming that inference-time category queries can be reliably grounded through pretraining-induced…
In the Complex Video Object Segmentation task, researchers are required to track and segment specific targets within cluttered environments, which rigorously tests a method's capability for target comprehension and environmental…
Few-Shot Video Object Segmentation (FSVOS) aims to segment objects in a query video with the same category defined by a few annotated support images. However, this task was seldom explored. In this work, based on IPMT, a state-of-the-art…
Video reasoning segmentation requires localizing objects across video frames from natural language expressions, often involving spatial reasoning and implicit references. Recent approaches leverage frozen large vision-language models…
Prompt design plays a crucial role in text-to-video (T2V) generation, yet user-provided prompts are often short, unstructured, and misaligned with training data, limiting the generative potential of diffusion-based T2V models. We present…
We present REM, a framework for segmenting a wide range of concepts in video that can be described through natural language. Our method leverages the universal visual-language mapping learned by video diffusion models on Internet-scale data…
In recent years, Multimodal Large Language Models (MLLMs) have made significant progress in visual question answering tasks. However, directly applying existing fine-tuning methods to remote sensing (RS) images often leads to issues such as…
Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision…
Referring image segmentation is a challenging task that involves generating pixel-wise segmentation masks based on natural language descriptions. The complexity of this task increases with the intricacy of the sentences provided. Existing…
In visual Reinforcement Learning (RL), learning from pixel-based observations poses significant challenges on sample efficiency, primarily due to the complexity of extracting informative state representations from high-dimensional data.…
Reasoning Video Object Segmentation is a challenging task, aiming at generating a mask sequence from an input video given a complex and implicit text query. While existing works finetune Multimodal Large Language Models (MLLM) for the task,…
Text-prompted image segmentation enables fine-grained visual understanding and is critical for applications such as human-computer interaction and robotics. However, existing supervised fine-tuning methods typically ignore explicit…
The performance of promptable video object segmentation (PVOS) models substantially degrades under input corruptions, which prevents PVOS deployment in safety-critical domains. This paper offers the first comprehensive study on robust PVOS…
Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose \textbf{VideoSeg-R1}, the first…
The current popular methods for video object segmentation (VOS) implement feature matching through several hand-crafted modules that separately perform feature extraction and matching. However, the above hand-crafted designs empirically…
As an important step towards visual reasoning, visual grounding (e.g., phrase localization, referring expression comprehension/segmentation) has been widely explored Previous approaches to referring expression comprehension (REC) or…